Zero discussion around LLM sampling. How do you leave such a gaping hole in such... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Der_Einzige 15 days ago \| parent \| context \| favorite \| on: The Bitter Lesson of LLM Extensions Zero discussion around LLM sampling. How do you leave such a gaping hole in such a written piece? I know it's not AI cus AI wouldn't be that sloppy.

ttkciar 15 days ago [–]

Local inference users are all about sampling, but users addicted to commercial inference services are wary of sampling, because they have to pay by the token.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact